© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103840
    Prev
    Next
    INDEX
    Explanations

    HTML, code, decoding

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on programming‐language import and module/class definition tokens (especially XML/etree import statements and related code identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tanzania
    -0.91
    Peterson
    -0.88
     Prophet
    -0.83
     Flüssigkeit
    -0.81
     Peterson
    -0.77
     glucose
    -0.76
     narcotic
    -0.73
     crystals
    -0.73
    LabelTagHelper
    -0.73
     Mozambique
    -0.72
    POSITIVE LOGITS
    jsoup
    1.01
     trovar
    0.89
     HTML
    0.78
    tbody
    0.74
    outdir
    0.73
    trums
    0.73
    sterne
    0.71
     ATX
    0.70
     brat
    0.69
    pagesize
    0.69
    Activations Density 0.052%

    No Known Activations